https://blog.herlein.com/tags/benchmarks/ Recent content in Benchmarks on Greg Herlein Hugo en &copy; 2018-2026. All rights reserved. Wed, 26 Aug 2026 09:00:00 -0700 https://blog.herlein.com/post/ai-agents-in-trenchcoats/ Wed, 26 Aug 2026 09:00:00 -0700 https://blog.herlein.com/post/ai-agents-in-trenchcoats/ <p>My experience is that Claude Code is great with Foundation Models, but way too heavy for local inference. I&rsquo;ve been enjoying oh-my-pi (omp) but was surprised that hax (a simpler agent in written in C) was TWICE as fast and used HALF the tokens! It&rsquo;s all about PREFILL<sup id="fnref:1"><a href="#fn:1" class="footnote-ref" role="doc-noteref">1</a></sup>. Read on!</p>